INDEX
Explanations
the word "im" in various contexts and forms
im followed by words
New Auto-Interp
Negative Logits
uſed
-0.74
pleaſure
-0.70
itſelf
-0.66
neſs
-0.65
ſtand
-0.64
tranſ
-0.62
ſta
-0.61
themſelves
-0.60
RIPRODUZIONE
-0.59
leſs
-0.57
POSITIVE LOGITS
im
1.05
in
1.03
Im
0.93
In
0.87
within
0.75
Im
0.73
IM
0.73
IN
0.68
במש
0.66
trong
0.65
Activations Density 0.001%